yw155

Hi @ZheC, could you provide the single-person CPM model trained on COCO. I would like to do single-person refinement on the multi-person pose predictions. Thank you in advance.

Hi @ZheC, I would like to ask you that what is the range of training loss on MPII dataset. I use MPI.json and masks you provided to generate lmdb. I...

Could you provide HigherHRNet testing models trained on CrowdPose dataset?

2

Could you provide HigherHRNet testing models trained on CrowdPose dataset? Thanks in advance.

How much is small and how much is large in real problem?

1

Hi @keskarnitish, I would like to ask a question that how much is a small batch and how much is a large batch in the real problems. For example, in...

Hi @kylemcdonald , could you explain how the deformation of face is handled, is there any reference paper?

Hi @anewell, I would like to ask you that how you handle the keypoints which are annotated at the position of (0, 0) during the training and inference. Is it...

How to handle the regions of people without annotations on COCO and MPII dataset?

1

Hi @anewell, I would like to ask a question that how to handle the people without annotations on COCO and MPII dataset. Do you think is it affect the training...

超图如何采集负样本？

4

您好，有个问题想向您请教下。 对于超图的监督学习，当采用二值化交叉熵损失函数，负样本空间中的组合情况特别多，这时负的超边该如何采样呢? 谢谢！

Hello @zcwang0702, thanks for sharing your interesting work. I have a question that how to set the input dimensions of bipartite networks if the input node numbers of drug or...

Hi @leonid-pishchulin, is it need to include the position of head box in the prediction file as the format of groundtruth? My method does not perform head part detection and...